Explore the vast range of titles available.

This paper presents a comprehensive spatiotemporal decomposition of equity returns for nine top-weighted constituents of the Dow Jones Industrial Average (DJIA) over a twenty-year period spanning January 2004 through December 2023, encompassing 5033 trading days and multiple market regimes, including the Global Financial Crisis (2008–2009), the COVID-19 crash and recovery (2020), and the Federal Reserve tightening cycle (2022–2023). Daily price movements are systematically partitioned into two orthogonal sessions: the open-to-close (OTC, or daytime) session, capturing within-session price discovery, and the close-to-open (CTO, or overnight) session, capturing the accumulated information arrival and liquidity dynamics between market closes and subsequent opens. Within this bipartite return framework, we construct and rigorously evaluate 24 distinct trading strategies, spanning directional (long/short), neutral (cash), momentum (inertia), and contrarian (reversal) approaches, applied independently to each session or in combinatorial cross-session configurations. Each strategy is evaluated under three transaction cost regimes (0, 1, and 2 basis points per trade) using an initial investment of100, and assessed using annualized return, annualised volatility, Sharpe ratio, Sortino ratio, and maximum drawdown. The study universe—comprising UnitedHealth Group (UNH), Goldman Sachs (GS), Microsoft (MSFT), Home Depot (HD), Caterpillar (CAT), Amgen (AMGN), McDonald’s (MCD), Salesforce (CRM), and Honeywell (HON)—captures cross-sector heterogeneity across Healthcare, Financials, Technology, Consumer Discretionary, Industrials, Biotech, and Consumer Staples. The universe is selected from the top-weighted DJIA constituents as of early 2026; the paper is, therefore, best read as a focused, in-depth case study of index-representative large-cap names rather than a general cross-sectional statement about all U.S. equities. The principal findings are threefold. First, the overnight session consistently delivers superior risk-adjusted performance: seven of nine stocks record higher Sharpe ratios during the overnight period versus the daytime period, with the mean overnight Sharpe ratio (0.662) substantially exceeding the mean daytime Sharpe ratio (0.357), a statistically and economically significant overnight premium. Second, the hybrid Strategy #18—Long Overnight coupled with Daytime Reversal—emerges as the dominant cross-asset configuration, generating portfolio values as high as 8464 from a 100 initial investment (AMGN; Sharpe: 0.991) over the 20-year horizon. Third, Trajectory Change Analysis reveals (i) Lévy-stable tails with a mean stability index α¯=1.667 across all constituents, substantially below the Gaussian benchmark of α=2.0; (ii) Hurst exponents clustering below 0.5 (H¯=0.417), confirming dominant mean-reverting dynamics; and (iii) positive rolling CAPM alpha in 51–79% of rolling windows, indicating persistent risk-adjusted outperformance above the S&P 500 benchmark. These findings provide a rigorous empirical foundation for session-aware algorithmic trading system design and challenge the prevailing assumption of temporal homogeneity in equity return processes.

Efficient management of bankruptcy risk requires treating distant-to-default (DD) stochastically as long as historical stock prices move randomly and, thus, do not guarantee that history may repeat itself. Using long-term data that date back to 1952–2023, including the nonfinancial companies listed in the Dow Jones Industrial Average and National Association of Securities Dealers Automated Quotations indexes, this study estimates the historical and stochastic DDs via the geometric Brownian motion (GBM). The results show that (a) the association between the debt-to-equity ratio and the stochastic DD can be used as an indicator of excessive debt financing; (b) debt tax savings have a positive effect on stochastic DD; (c) bankruptcy costs have negative effects on stochastic DD; (d) in terms of the size of the company being proxied by sales revenue and the equity market value of the company, the DD is a reliable measure of bankruptcy costs; (e) in terms of macroeconomic influences, increases in the percentage change in manufacturing output are associated with lower observed and stochastic DD; and (f) in terms of the influences of industry, the stochastic DD is affected by the industry average retail inventory to sales. This paper contributes to related studies in terms of focusing on the indicators that a company’s management can focus on to address the stochastic patterns inherent in the estimation of the DD.

The aim of this paper is to propose a method for selecting underlying assets for the investment portfolio so that we can achieve a maximum expected return with minimal risk. For this purpose, we describe the portfolio creation process using the minimum spanning tree method, a graph theory tool. Using this theory, we select individual stocks from the Dow Jones Industrial Average index which we include in the portfolio and then compare the performance of such a portfolio with three alternative investments. The first alternative investment is a purchase of the entire Dow Jones Industrial Average index, the second alternative investment is to create a portfolio according to the Markowitz portfolio theory, and the third alternative investment is to create a portfolio through a random selection of indexforming stocks. The comparison was made mainly with regard to the average annual return and volatility of portfolios. In order to ensure the objectivity of the results, we divided the data into two disjoint sets. One of them was a training set, on which we built the portfolio, and the other one was a testing set used for performance testing. In the article we present that our portfolio can achieve results at least as good as those of the given alternative investments. In particular, this method also enables individual investors to determine how many underlying assets should be included in the portfolio.

PurposeThe purpose of this paper is to examine changes in stock returns, liquidity, institutional ownership, analyst following and investor awareness for companies added to and deleted from the Dow Jones Industrial Average (DJIA) index. Previous studies report conflicting evidence regarding the market reactions to changes in the DJIA index membership.Design/methodology/approachThis study uses the event-study methodology to calculate abnormal returns and trading volume around the announcement and effective days of DJIA index changes from 1929 to 2015. It also tests for significant changes in liquidity, institutional ownership, analyst following and investor awareness in the 1990–2015 period. Multivariate regressions are used to perform a simultaneous analysis of competing hypotheses.FindingsThis study resolves the mixed results of previous DJIA index papers by documenting different stock price and trading volume reactions over the 1929–2015 period. Focusing on the most recent period, 1990–2015, the study finds that stocks added to (deleted from) the index experience a significant permanent stock price gain (loss). The observed stock price reaction seems to be associated with changes in liquidity proxies thus lending support for the liquidity hypothesis.Research limitations/implicationsLimited data availability for the periods prior to 1990 prevents this study from identifying the exact reasons for different stock price and trading volume reactions across subperiods of the 1929–2015 period.Originality/valueThis study provides the most comprehensive examination of market reactions to changes in the DJIA index and resolves the mixed results of previous studies. A better understanding of market reactions around the DJIA index changes can help both individual and institutional investors with developing effective trading strategies and index managing companies with designing optimal announcement policies.

Social media are increasingly reflecting and influencing behavior of other complex systems. In this paper we investigate the relations between a well-known micro-blogging platform Twitter and financial markets. In particular, we consider, in a period of 15 months, the Twitter volume and sentiment about the 30 stock companies that form the Dow Jones Industrial Average (DJIA) index. We find a relatively low Pearson correlation and Granger causality between the corresponding time series over the entire time period. However, we find a significant dependence between the Twitter sentiment and abnormal returns during the peaks of Twitter volume. This is valid not only for the expected Twitter volume peaks (e.g., quarterly announcements), but also for peaks corresponding to less obvious events. We formalize the procedure by adapting the well-known \"event study\" from economics and finance to the analysis of Twitter data. The procedure allows to automatically identify events as Twitter volume peaks, to compute the prevailing sentiment (positive or negative) expressed in tweets at these peaks, and finally to apply the \"event study\" methodology to relate them to stock returns. We show that sentiment polarity of Twitter peaks implies the direction of cumulative abnormal returns. The amount of cumulative abnormal returns is relatively low (about 1-2%), but the dependence is statistically significant for several days after the events.

The Halloween effect is one of the most famous calendar anomalies. It is based on the observation that stock returns tend to perform much better over the winter half of the year (November-April) than over the summer half of the year (May-October). The vast majority of studies that investigated the Halloween effect over the recent decades focused only on stock indices. This means that they evaluated whether a stock index follows the Halloween effect pattern, but they omitted digging a little deeper and analyze the Halloween effect on the individual stocks level. This paper investigates to what extent the blue-chips stocks included in the Dow Jones Industrial Average are affected by the Halloween effect and whether the Halloween effect is widespread or the behavior of the whole index is driven by only a handful of stocks that are strongly affected by the Halloween effect. The results show that, although the strength of the Halloween effect varies quite rapidly from stock to stock, the vast majority of analyzed stocks experienced a notably higher average winter period than summer period returns over the 1980-2017 period. Moreover, in 18 out of 35 cases, the Halloween effect was statistically significant.

The aims of this study are to predict the stock price trend in the stock market in an emerging economy. Using the Long Short Term Memory (LSTM) algorithm, and the corresponding technical analysis indicators for each stock code include: simple moving average (SMA), convergence divergence moving average (MACD), and relative strength index (RSI); and the secondary data from VN-Index and VN-30 stocks, the research results showed that the forecasting model has a high accuracy of 93% for most of the stock data used, demonstrating the appropriateness of the LSTM model and the test set data is used to evaluate the model’s performance. The research results showed that the forecasting model has a high accuracy of 93% for most of the stock data used, demonstrating the appropriateness of the LSTM model in analyzing and forecasting stock price movements on the machine learning platform.

Stock market has received widespread attention from investors. It has always been a hot spot for investors and investment companies to grasp the change regularity of the stock market and predict its trend. Currently, there are many methods for stock price prediction. The prediction methods can be roughly divided into two categories: statistical methods and artificial intelligence methods. Statistical methods include logistic regression model, ARCH model, etc. Artificial intelligence methods include multi-layer perceptron, convolutional neural network, naive Bayes network, back propagation network, single-layer LSTM, support vector machine, recurrent neural network, etc. But these studies predict only one single value. In order to predict multiple values in one model, it need to design a model which can handle multiple inputs and produces multiple associated output values at the same time. For this purpose, it is proposed an associated deep recurrent neural network model with multiple inputs and multiple outputs based on long short-term memory network. The associated network model can predict the opening price, the lowest price and the highest price of a stock simultaneously. The associated network model was compared with LSTM network model and deep recurrent neural network model. The experiments show that the accuracy of the associated model is superior to the other two models in predicting multiple values at the same time, and its prediction accuracy is over 95%.

The accelerated progress in artificial intelligence encourages sophisticated deep learning methods in predicting stock prices. In the meantime, easy accessibility of the stock market in the palm of one’s hand has made its behavior more fuzzy, volatile, and complex than ever. The world is looking at an accurate and reliable model that uses text and numerical data which better represents the market’s highly volatile and non-linear behavior in a broader spectrum. A research gap exists in accurately predicting a target stock’s closing price utilizing the combined numerical and text data. This study uses long short-term memory (LSTM) and gated recurrent unit (GRU) to predict the stock price using stock features alone and incorporating financial news data in conjunction with stock features. The comparative study carried out under identical conditions dispassionately evaluates the importance of incorporating financial news in stock price prediction. Our experiment concludes that incorporating financial news data produces better prediction accuracy than using the stock fundamental features alone. The performances of the model architecture are compared using the standard assessment metrics —Root Mean Square Error (RMSE), Mean Absolute Percentage Error (MAPE), and Correlation Coefficient (R). Furthermore, statistical tests are conducted to further verify the models’ robustness and reliability.

The use of Machine Learning (ML) and Sentiment Analysis (SA) on data from microblogging sites has become a popular method for stock market prediction. In this work, we developed a model for predicting stock movement utilizing SA on Twitter and StockTwits data. Stock movement and sentiment data were used to evaluate this approach and validate it on Microsoft stock. We gathered tweets from Twitter and StockTwits, as well as financial data from Finance Yahoo. SA was applied to tweets, and seven ML classification models were implemented: K-Nearest Neighbors (KNN), Support Vector Machine (SVM), Logistic Regression (LR), Naïve Bayes (NB), Decision Tree (DT), Random Forest (RF) and Multilayer Perceptron (MLP). The main novelty of this work is that it integrates multiple SA and ML methods, emphasizing the retrieval of extra features from social media (i.e., public sentiment), for improving stock prediction accuracy. The best results were obtained when tweets were analyzed using Valence Aware Dictionary and sEntiment Reasoner (VADER) and SVM. The top F-score was 76.3%, while the top Area Under Curve (AUC) value was 67%.